More Like this

1. Resiliency Assessment in Distribution Networks Using GIS Based Predictive Risk Analytics,”

   J. Leite, J. Mantovani (January 2018, IEEE PES 2018 Transmission and Distribution Latin America (T&D LA), Peru, Sep. 18-21, 2018.)

   A new predictive risk-based framework is proposed to increase power distribution network resiliency by improving operator understanding of the energy interruption impacts. This paper expresses the risk assessment as the correlation between likelihood and impact. The likelihood is derived from the combination of Naive Bayes learning and Jenks natural breaks classifier. The analytics included in a GIS platform fuse together a massive amount of data from outage recordings and weather historical databases in just one semantic parameter known as failure probability. The financial impact is determined by a time series-based formulation that supports spatiotemporal data from fault management events and customer interruption cost. Results offer prediction of hourly risk levels and monthly accumulated risk for each feeder section of a distribution network allowing for timely risk mitigation. 

   more » « less
2. “Optimized Asset Management in Distribution Systems Based on Predictive Risk Analysis

   T. Dokic, M. Kezunovic (January 2018, Energies)

   The paper introduces an optimal maintenance scheduler based on predictive assessment of risk of outage and equipment failure in distribution networks. The variety of severe weather conditions are observed and their impact on the network components is quantified. The equipment deterioration and failure rates are observed continuously across the space and time using heterogeneous data. The risk of weather-related outages for each component is generated in real-time, and can be extracted at multiple temporal and spatial scales depending on the application of interest. The optimal maintenance scheduling that minimizes the system risk while maintaining the economic investment limits is developed. The benefits of the framework are presented using a distribution network asset management example. 

   more » « less
3. Fast parameter estimation of generalized extreme value distribution using neural networks

   https://doi.org/10.1002/env.2845  

   Rai, Sweta; Hoffman, Alexis; Lahiri, Soumendra; Nychka, Douglas W.; Sain, Stephan R.; Bandyopadhyay, Soutir (March 2024, Environmetrics)

   Abstract The heavy‐tailed behavior of the generalized extreme‐value distribution makes it a popular choice for modeling extreme events such as floods, droughts, heatwaves, wildfires and so forth. However, estimating the distribution's parameters using conventional maximum likelihood methods can be computationally intensive, even for moderate‐sized datasets. To overcome this limitation, we propose a computationally efficient, likelihood‐free estimation method utilizing a neural network. Through an extensive simulation study, we demonstrate that the proposed neural network‐based method provides generalized extreme value distribution parameter estimates with comparable accuracy to the conventional maximum likelihood method but with a significant computational speedup. To account for estimation uncertainty, we utilize parametric bootstrapping, which is inherent in the trained network. Finally, we apply this method to 1000‐year annual maximum temperature data from the Community Climate System Model version 3 across North America for three atmospheric concentrations: 289 ppm (pre‐industrial), 700 ppm (future conditions), and 1400 ppm , and compare the results with those obtained using the maximum likelihood approach. 

   more » « less
4. Risk-Based Hosting Capacity Analysis in Distribution Systems

   https://doi.org/10.1109/TPWRS.2023.3238846  

   Madavan, Avinash N.; Dahlin, Nathan; Bose, Subhonmesh; Tong, Lang (January 2024, IEEE Transactions on Power Systems)

   Solar hosting capacity analysis (HCA) assesses the ability of a distribution network to host distributed solar generation without seriously violating distribution network constraints. In this paper, we consider risk-sensitive HCA that limits the risk of network constraint violations with a collection of scenarios of solar irradiance and nodal power demands, where risk is modeled via the conditional value at risk (CVaR) measure. First, we consider the question of maximizing aggregate installed solar capacities, subject to risk constraints and solve it as a second-order cone program (SOCP) with a standard conic relaxation of the feasible set of the power flow equations. Second, we design an incremental algorithm to decide whether a configuration of solar installations has acceptable risk of constraint violations, modeled via CVaR. The algorithm circumvents explicit risk computation by incrementally constructing inner and outer polyhedral approximations of the set of acceptable solar installation configurations from prior such tests conducted. Our numerical examples study the impact of risk parameters, the number of scenarios and the scalability of our framework. 

   more » « less
5. Distributionally Robust Structure Learning for Discrete Pairwise Markov Networks

   Li, Yeshu; Shi, Zhan; Zhang, Xinhua; Ziebart, Brian (March 2022, International Conference on Artificial Intelligence and Statistics)

   We consider the problem of learning the underlying structure of a general discrete pairwise Markov network. Existing approaches that rely on empirical risk minimization may perform poorly in settings with noisy or scarce data. To overcome these limitations, we propose a computationally efficient and robust learning method for this problem with near-optimal sample complexities. Our approach builds upon distributionally robust optimization (DRO) and maximum conditional log-likelihood. The proposed DRO estimator minimizes the worst-case risk over an ambiguity set of adversarial distributions within bounded transport cost or f-divergence of the empirical data distribution. We show that the primal minimax learning problem can be efficiently solved by leveraging sufficient statistics and greedy maximization in the ostensibly intractable dual formulation. Based on DRO’s approximation to Lipschitz and variance regularization, we derive near-optimal sample complexities matching existing results. Extensive empirical evidence with different corruption models corroborates the effectiveness of the proposed methods. 

   more » « less